PulseAugur
EN
LIVE 17:29:00
한국어(KO) osFoundry는 왜 Claude Code의 툴 허용 목록을 CLI 플래그가 아니라 MCP 서버에 둘까

osFoundry enforces Claude Code tool security server-side

By PulseAugur Editorial · [4 sources] ·

The osFoundry desktop application implements a server-side security model for its interaction with Claude Code, prioritizing server-side control over client-side flags. This approach ensures that the server, not the client, dictates which tools are available and executable. osFoundry achieves this by filtering tool lists on the server and verifying tool calls before execution, even when Claude Code is in a bypass permissions mode. This design prevents the model from accessing or invoking unauthorized tools, even if they are present in its training data or introduced via prompt injection. AI

IMPACT Enhances security for LLM-powered applications by centralizing tool access control on the server.

RANK_REASON The article details a specific implementation choice for tool security within a desktop application interacting with an LLM, rather than a novel model release or core research.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

osFoundry enforces Claude Code tool security server-side

How we ranked this

Signal score
14 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The article details a specific implementation choice for tool security within a desktop application interacting with an LLM, rather than a novel model release or core research.
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [4]

  1. dev.to — MCP tag TIER_1 한국어(KO) · BBT ·

    Why does osFoundry put Claude Code's tool allowlist on the MCP server instead of a CLI flag?

    <p><a href="https://osfoundry.io/ko" rel="noopener noreferrer">osFoundry</a> 데스크톱 앱은 Claude Code를 에이전트 모드 워커로 띄울 때 아래 MCP 설정을 넘긴다. 포트와 토큰은 내가 Python으로 다시 짠 브리지를 돌렸을 때 나온 값이다. 구조는 <code>src-tauri/src/mcp_bridge.rs</code>와 같다.<br /> </p> <div class="highlight js-code-highlight"> <p…

  2. dev.to — MCP tag TIER_1 Français(FR) · BBT ·

    Why osFoundry applies Claude Code server-side MCP allowlist and not via CLI flags

    <p>Voici la configuration MCP que l'application de bureau <a href="https://osfoundry.io/fr" rel="noopener noreferrer">osFoundry</a> transmet à Claude Code quand elle le lance comme worker en mode agent. Le bridge utilisé ici est ma réimplémentation en Python, donc le port et le t…

  3. dev.to — MCP tag TIER_1 中文(ZH) · BBT ·

    Why does osFoundry whitelist Claude Code tools on the MCP server instead of in CLI arguments?

    <p>這是 <a href="https://osfoundry.io/zh" rel="noopener noreferrer">osFoundry</a> 桌面 app 以 agent mode worker 身分執行 Claude Code 時，交給它的 MCP 設定。這裡的 bridge 是我用 Python 重建的版本，所以 port 和 token 都來自那次執行。結構則和 <code>src-tauri/src/mcp_bridge.rs</code> 裡的一樣：<br /> </p> <div class="highlight js-co…

  4. dev.to — MCP tag TIER_1 English(EN) · BBT ·

    Why osFoundry enforces Claude Code's tool allowlist on the MCP server, not in CLI flags

    <p>This is the MCP config the <a href="https://osfoundry.io" rel="noopener noreferrer">osFoundry</a> desktop app hands to Claude Code when it runs it as an agent-mode worker. The bridge here is my Python rebuild, so the port and token are from that run. The shape is the one in <c…

RELATED ENTITIES

RELATED TOPICS